Automated Skill Discovery and Dynamic Matching via Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for managing agent skills in ITSM service desks are cumbersome, error-prone, and inefficient, as they rely on manual curation and fail to accurately track dynamic skill changes, leading to suboptimal ticket routing and skill utilization.
Innovation Solution
A computer-implemented method using machine learning and AI to automatically discover and compute agent skills through a clustering algorithm, generating a skills matrix or knowledge graph that dynamically updates based on ticket resolutions, enabling intelligent skill matching and routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual skills management is used, then skills can be tracked, but it is error-prone and inaccurate due to dynamic skill changes
Solution Approach 1:
The system enables automatic self-updating of skills data by extracting skill information directly from ticket data and resolutions. The skills matrix automatically evolves as new tickets are processed, eliminating the need for manual skills management while maintaining high accuracy through data-driven skill extraction and clustering algorithms.
Solution Approach 2:
The patent replaces manual mechanical skills management processes with automated computational systems including clustering algorithms, taxonomy construction algorithms, and machine learning models that automatically discover, organize, and update skills from ticket data, eliminating human error and time consumption.
2Adaptability or versatility
If manual skills curation is used, then skills can be defined, but it is complicated and time-consuming involving many variables
Solution Approach 1:
The system segments skills into hierarchical taxonomies with parent-child relationships, organizing complex skills into manageable categories and subcategories. This segmentation allows the system to handle skill complexity systematically while automatically discovering and organizing skills from ticket data without manual intervention.
Solution Approach 2:
The skills matrix is designed to be dynamic and automatically adapts as new skills are discovered from ticket data. The system continuously evolves the skills taxonomy and agent skill profiles based on incoming tickets and resolutions, eliminating the need for static manual curation while reducing management complexity.
3Productivity
If automated skill discovery is implemented, then ticket routing efficiency improves, but system complexity increases
Solution Approach 1:
The system implements feedback loops where ticket resolution outcomes automatically update agent skill profiles and the skills matrix. This feedback mechanism continuously improves routing accuracy and system performance while maintaining manageable complexity through automated learning from real-world ticket data rather than requiring complex predefined rules.
Solution Approach 2:
The skills matrix serves multiple functions simultaneously: it routes tickets to appropriate agents, tracks skill development, identifies training needs, and supports organizational knowledge management. This multi-functionality achieves high productivity across multiple objectives without proportionally increasing system complexity.
Data Source
AI summary
A system, method, and computer program product for intelligent-skills-matching includes receiving a plurality of tickets, where each ticket in the plurality of tickets includes a plurality of fields and at least one agent who resolved the ticket is identified. A clustering algorithm is used on one or more of the plurality of fields to determine skills from the plurality of tickets. A taxonomy of the skills is generated using a taxonomy-construction algorithm. Using the taxonomy of the skills, a skills matrix or a skills knowledge graph is created with agents assigned to the skills.